auto-updater

Automatically update OpenClaw and selected skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.

2.00x

Quality

70%

Does it follow best practices?

Impact

98%

2.00x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./clawdbot/auto-updater/SKILL.md

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and highly actionable with copy-paste-ready commands, but the multi-step batch update workflow lacks an explicit validation feedback loop, and the two provided reference files are not surfaced from the body. Linking the bundle references would materially improve discoverability.

Suggestions

Add explicit validation checkpoints to the update workflow (e.g. after the update run, verify `openclaw --version` changed and re-run `doctor --fix` if it failed, looping until healthy).

Link the existing bundle files from the body, e.g. a '## Implementation guide' section pointing to references/agent-guide.md and a '## Summary format' section pointing to references/summary-examples.md.

De-duplicate the cron-add command between the body and references/agent-guide.md so the body links to the canonical detailed version rather than repeating it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, using tight code blocks and brief section intros without explaining concepts Claude already knows. Not a 2 because there is no padded exposition or unnecessary library/concept explanation.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout (cron add, npm update -g openclaw@latest, openclaw doctor --fix, gateway restart, clawhub update --all, clawhub list, openclaw --version, cron remove). Not a 2 because the commands are concrete and complete rather than pseudocode.	3 / 3
Workflow Clarity	A sequence is present (setup → updates → troubleshooting) but there is no explicit validate→fix→retry feedback loop for a global batch update, which the guidelines cap at 2. Not a 3 because checkpoints are implicit; not a 1 because steps are clearly listed.	2 / 3
Progressive Disclosure	Sections are well-organized, but the existing bundle files references/agent-guide.md and references/summary-examples.md are never linked or signaled from the body, so navigation to the detailed material is missing. Not a 3 because references are not clearly signaled; not a 1 because the body is organized, not a monolithic wall of text or nested references.	2 / 3
	Total	10 / 12 Passed

Description

60%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and uses correct third-person voice, clearly conveying what the skill does, but it omits any 'Use when...' trigger guidance, capping completeness and leaving trigger-term coverage incomplete. Conflict risk is moderate due to the lack of explicit distinguishing triggers.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to keep OpenClaw and skills up to date, set up auto-updates, or schedule daily updates.'

Broaden trigger terms to include natural variations users would say ('auto-update', 'upgrade', 'keep up to date', 'schedule updates') alongside 'update' and 'cron'.

Tie the distinctiveness hook to the cron-scheduled, daily, summary-delivered nature of the skill so it is less likely to fire for one-off manual update requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('update OpenClaw and selected skills', 'Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed'), matching the multiple-specific-actions anchor. Not a 2 because it goes beyond naming a domain plus a couple of actions.	3 / 3
Completeness	Clearly answers 'what' it does but provides no 'Use when...' or equivalent explicit trigger guidance, which the guidelines cap at 2. Not a 3 because 'when' is entirely missing rather than explicit.	2 / 3
Trigger Term Quality	Contains relevant keywords ('update', 'skills', 'cron') but misses common natural variations a user might say ('upgrade', 'keep up to date', 'auto-update'). Not a 3 because coverage of natural terms is incomplete; not a 1 because usable keywords are present.	2 / 3
Distinctiveness Conflict Risk	The auto-update niche is somewhat specific but lacks explicit triggers and could overlap with ordinary manual update requests. Not a 3 because conflict risk with generic 'update' intents remains; not a 1 because it is not broadly generic.	2 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: jdrhyne/agent-skills
Path: clawdbot/auto-updater/SKILL.md
Commit: a4d31ad

Reviewed: 21 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.